# ScreenSpot Pro → Video-MME (with subtitle)

Calibration · https://benchgap.net/calibration/1419 · data retrieved 2026-10-29

Video-MME (with subtitle) is estimated from ScreenSpot Pro with a linear curve fitted on 6 models measured on both: y = 0.4573·x + 0.5277, R² = 0.63, cross-validated error 7.2 pp. It is used for 4 estimates.

| Estimated model | ScreenSpot Pro | Video-MME (with subtitle) | Source |
|---|---|---|---|
| [Holo2-235B-A22B](https://benchgap.net/model/holo2-235b-a22b.md) | 70.6% | 85.1% | estimated ± 7.2 pp, low confidence |
| [Holo2-30B-A3B](https://benchgap.net/model/holo2-30b-a3b.md) | 66.1% | 83.0% | estimated ± 7.2 pp, low confidence |
| [Holo2-8B](https://benchgap.net/model/holo2-8b.md) | 58.9% | 79.7% | estimated ± 7.2 pp, low confidence |
| [Holo2-4B](https://benchgap.net/model/holo2-4b.md) | 57.2% | 78.9% | estimated ± 7.2 pp, low confidence |

## Fitted on

| Model | ScreenSpot Pro | Video-MME (with subtitle) |
|---|---|---|
| [Claude Opus 4.5](https://benchgap.net/model/claude-opus-4-5.md) | 45.7% | 77.6% |
| [Gemini 3 Pro](https://benchgap.net/model/gemini-3-pro.md) | 72.7% | 88.4% |
| [LFM3-VL-2B](https://benchgap.net/model/lfm3-vl-2b.md) | 55.5% | 69.0% |
| [Qwen3.5 397B](https://benchgap.net/model/qwen3-5-397b.md) | 65.6% | 87.5% |
| [Qwen3.7 Plus](https://benchgap.net/model/qwen3-7-plus.md) | 79.0% | 88.0% |
| [Qwen3.8 Max](https://benchgap.net/model/qwen3-8-max.md) | 84.5% | 90.4% |